© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214671
    Prev
    Next
    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strath
    0.40
     preparazione
    0.38
     stro
    0.38
    stro
    0.37
     mez
    0.36
    鸟
    0.36
     mej
    0.36
    濃
    0.36
    ដ្ឋ
    0.36
     preparación
    0.36
    POSITIVE LOGITS
    灏
    0.42
     Assumption
    0.42
     अल्फा
    0.40
    Richmond
    0.40
    fork
    0.38
     চুপ
    0.38
     Chilton
    0.38
     Richmond
    0.38
     forks
    0.38
    ℏ
    0.38
    Activations Density 0.000%

    No Known Activations